Synthesizing Feature Extractors: An Agentic Approach for Algorithm Selection

arXiv:2608.17170v1 Announce Type: new Abstract: Algorithm selection for constraint satisfaction problems requires extracting features that capture problem structure. Manually designing feature extractors demands deep domain expertise and quickly becomes a bottleneck when new problem classes appear. We present an automated approach that uses Large Language Models (LLMs) in an agentic check--fix--verify loop to synthesize executable Python scripts that act as interpretable, problem-specific feature extractors. Given a high-level MiniZinc model and an instance, the LLM agent generates code that constructs a typed graph representation and computes structural properties such as graph density, variable clustering, and constraint tightness. We evaluate our approach on three combinatorial problems (vehicle routing, car sequencing, fixed-length error-correcting codes) with a portfolio of five state-of-the-art solvers. The synthesized extractors yield algorithm selectors that consistently outperform both expert-curated mzn2feat features (up to 8.3 percentage points (pp) test-set accuracy on FLECC) and the best transformer-based trans2feat variants. In the meanwhile, the synthesized feature extractors remain inspectable.

Related

• A Dual-Helix Governance Approach Towards Reliable Agentic Artificial Intelligence for WebGIS Development
• OR-Agent: Bridging Evolutionary Search and Structured Research for Automated Algorithm Discovery
• QuantumMind: Constraint-Grounded Agentic Reasoning for Speedup Analysis in Quantum Computing

Source: arXiv cs.AI | 2026-08-19